De-homogenization using convolutional neural networks

DOI10.1016/J.CMA.2021.114197MaRDI QIDQ2060089zbMATH OpenOpenAlexFDO

Authors Martin Ohrt Elingaard, Niels Aage, Jakob Andreas Bærentzen, Ole Sigmund

Publication date 13 December 2021

Published in Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2105.04232

zbMATH Keywords

deep learningtopology optimizationconvolutional neural networksde-homogenization

Mathematics Subject Classification ID

Compliance or weight optimization in solid mechanics (74P05) Topological methods for optimization problems in solid mechanics (74P15)

Recommendations

• Generalized de-homogenization via sawtooth-function-based mapping and its demonstration on data-driven frequency response optimization
• A deep convolutional neural network for topology optimization with perceptible generalization ability
• Isogeometric topology optimization based on deep learning
• Neural networks for topology optimization
• Topology optimization based on deep representation learning (DRL) for compliance and stress-constrained design

Cites work

• scientific article; zbMATH DE number 1300255 (Why is no real title available?)
• scientific article; zbMATH DE number 2038815 (Why is no real title available?)
• A Post-Treatment of the Homogenization Method for Shape Optimization
• Advanced Lectures on Machine Learning
• De-homogenization of optimal multi-scale 3D topologies
• Deep generative modeling for mechanistic-based learning and design of metamaterial systems
• Generating optimal topologies in structural design using a homogenization method
• Homogenization-based stiffness optimization and projection of 2D coated structures with orthotropic infill
• Material interpolation schemes in topology optimization
• On projection methods, convergence and robust formulations in topology optimization
• Topology optimization of modulated and oriented periodic microstructures by the homogenization method
• Universal machine learning for topology optimization

Cited in

(11)

• Neural Network Deinterlacing Using Multiple Fields
• Training Very Deep CNNs for General Non-Blind Deconvolution
• Porous structure reconstruction using convolutional neural networks
• Deep learning and multi-level featurization of graph representations of microstructural data
• Topology optimization via implicit neural representations
• Deep learning in computational mechanics: a review
• Compliance minimisation of smoothly varying multiscale structures using asymptotic analysis and machine learning
• Generalized de-homogenization via sawtooth-function-based mapping and its demonstration on data-driven frequency response optimization
• Design and optimization of functionally-graded triangular lattices for multiple loading conditions
• Relaxation network for Gabor image decomposition
• Phasor noise for dehomogenisation in 2D multiscale topology optimisation

This page was built for publication: De-homogenization using convolutional neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2060089)